Skip to content
WorkPressAboutRésuméContact ben@peeri.us
AI Solutions Architect · 2x Founder-CEO · TEDx Speaker

I build the program, and I ship the product.

A hands-on AI leader who stands up AI-native organizations where people and AI agents ship together. Proven inside a Fortune 150 enterprise and as a two-time founder-CEO. Credible in the boardroom and in the build.

See the workGet in touch
  • TEDx speaker · ~125K views
  • Ex-JPMorgan Chase VP
  • Patent-pending inventor
  • $5M+ cost avoidance
// currently shippinglive

  • Enterprise Mobility

    Lead AI Solutions Architect, R&D

  • Meat Bot

    1st unit live on a USDA line

  • Chicken Butt Jerky

    Run by a 14-agent workforce

the conductor model

155agent commitsvs16human

$5M+
cost avoidance

AI-agent network-outage analysis at Fortune 150 scale, plus ~45% faster delivery.

14
AI solutions in production

End-to-end solutions and reusable blueprints on a private, in-tenant Azure GenAI platform.

131
model deployments

Self-hosted in-tenant across 8 providers, behind one governed, SSO-gated workspace.

<90 days
idea to launched brand

Bootstrapped an AI-native CPG brand from zero to shipping on ~$25K, in an industry with no prior experience.

~125K
TEDx views
254K+
knowledge chunks indexed
40%
shorter support calls
80%
faster incident response
16
person team, 5 countries
2
provisional patents

Every number here is actual and shipped. No projections. No slideware.

The method

I don't just direct AI. I conduct it.

I treat building software like conducting, not typing. I direct a workforce of AI agents, digital employees, and pull in human specialists only where the agents can't reproduce the result. The proof isn't a diagram. It is in the git log.

01

Agents do the work

Across my product repos, AI agent personas author the majority of the commits. I own the architecture, the reviews, and the outcome.

02

AI-first, human where it counts

AI-first until the agents can't reproduce the result, then a human SME arrives at an idea that already has gravity, a spec, artifacts, direction, and just trims and optimizes.

03

One human, ~ten agents

I run a roughly 1-human-to-10-agents team where humans receive work from the agents, not the reverse. If you can manage a distributed offshore team, you can manage AI agents.

$ git shortlog -sngit-authorship on the Hermes platform
AI agent personas155 commits
Ben (architect / reviewer)16 commits

AI agent personas author the majority of commits. I operate as architect and reviewer. This is the conductor model in version control.

91%
authored by agents
1 : ~10
human : agents
AI-first
operating rule
Selected work

Shipped systems, not slideware.

A sample across the range: agentic platforms, enterprise RAG, voice AI, physical robotics, and companies run by agents. Each tagged with exactly what I did.

All 22 projects
BuiltEnterprise Mobility

SaaS-Hermes

A zero-trust agentic research workspace

Six specialist research agents work alongside a strategy team on Azure Container Apps, each with its own persona, methodology, citation rules, and cross-referral handoffs. Shared team memory compounds over time; a curated RAG index grounds every answer; frontier models run entirely in-tenant. Zero external LLM calls.

  • 6 specialist agents
  • 17 containerized services
  • 19 lint-enforced invariants
  • 0 external LLM calls

Azure AI Foundry · Container Apps · Azure AI Search · MCP · WebRTC · FastAPI

ArchitectedEnterprise Mobility

Private Enterprise GenAI Platform

The in-tenant control plane every solution plugs into

A fully in-tenant Azure AI platform where no inference or data ever leaves the company tenant. One governed, SSO-gated workspace delivering multi-model chat, agentic RAG, voice AI, and document intelligence, plus the reusable blueprints that turn one-off builds into a repeatable platform.

  • 14 solutions
  • 131 model deployments
  • ~45 MCP tools
  • 36+ Container Apps in a private VNet

Azure · Private VNet · Entra SSO · Managed Identity · OpenWebUI · LiteLLM

BuiltChicken Butt Jerky · Meat Bot

Meat Bot

An AI-designed food-production robot, running daily on a USDA line

Designed, built, and deployed the first production unit into a USDA-inspected co-packer. AI generated the CAD for custom nozzles, designed the circuits, and helped write the firmware. Real hardware: a custom KiCad PCB (two fabricated revisions) with an ESP32-S3 and GRBL motion control, OTA updates, and a cloud fleet-management backend. Proof that agent-orchestrated AI solves physical problems, not just digital ones.

  • 1st production unit deployed
  • running daily since 2026
  • 2 provisional patents
  • AI-generated CAD + firmware

ESP32-S3 · KiCad · GRBL · OTA firmware · Google Cloud Run · Supabase

meat-bot.com
BuiltChicken Butt Jerky · Meat Bot

Hermes

A company-in-a-box: 14 AI agents run the business

A self-hosted platform of 14 named AI agents (CEO advisor, operations, sales, marketing, finance, support, and more) that run Chicken Butt Jerky's business functions, with cross-agent long-term memory. The proof of the conductor model lives in the git log: agent personas author the majority of commits, with a human architect and reviewer.

  • 14 named agents
  • ~155 agent commits vs 16 human
  • 10 vendored MCP integrations
  • no public IPs (Tailscale)

GKE Autopilot · Honcho + pgvector · OpenWebUI · Telegram · Terraform · Helm

chickenbuttjerky.com
BuiltEnterprise Mobility

CCC Intelligence Hub

Document intelligence that collapses weeks into hours

A 7-stage pipeline that scrapes a gated external portal, enriches every document with AI summaries and extracted action items, and serves it all as searchable knowledge, compressing weeks of manual review into a 2-hour auto-refresh cycle.

  • 254K+ chunks
  • 2,409 AI summaries
  • 4,763 action items
  • 2-hour refresh (from weeks)

Playwright · Python · Azure AI Search · PostgreSQL · Blob Storage

BuiltEnterprise Mobility

Call-Center Chatbot

Conversational AI with proven ROI

A pilot agent that lets support reps retrieve data and answer customer questions in natural language, surfacing answers in the conversation instead of hunting across systems. Direct proof of conversational AI tied to a measurable business outcome.

  • 40% shorter calls
  • +23% accuracy
  • +17% CSAT
  • 98% response accuracy in pilot

RAG · LLM retrieval · Conversational UX

The path

Twenty years of enterprise, reinvented as a builder.

Systems to security to cloud to VP, then founder. The same arc that took me into the boardroom keeps me in the codebase.

Full story & career

  1. Enterprise Mobility

    Sep 2023 - Present

    Lead AI Solutions Architect, R&D Innovation · Remote

    Lead the AI innovation program at a Fortune 150 mobility enterprise as a de facto AI center of excellence: scouting emerging AI, architecting solutions, pitching senior leadership, and productionizing the platforms other teams build on.

    • Delivered $5M+ cost avoidance and ~45% faster delivery through AI-agent automation for network-outage analysis.
    • Architected a private, in-tenant Azure GenAI platform: 14 solutions, 131 model deployments, 254K+ indexed chunks, ~45 MCP tools.
    • Led an enterprise API-security evaluation (a 140-requirement scoring matrix) and briefed the C-suite on vendor strategy.
    • Mentor engineers and business partners; represent the org to an industry connected-vehicle consortium.
    current

  2. Chicken Butt Jerky · Meat Bot

    Jul 2025 - Present

    Founder, CEO & AI/Tech Lead · McKinney, TX

    Founded an AI-native CPG brand and a companion food-automation hardware line, run end-to-end by two founders plus an AI agent workforce.

    • Designed, built, and deployed the first production robot into a USDA-inspected co-packer, running daily since 2026.
    • Launched the brand in under 90 days on ~$25K bootstrapped, in an industry with zero prior experience.
    • Filed 2 U.S. provisional patents (patent-pending); trademark applications in prosecution.
    • Run marketing, operations, accounting, and CRM through a 14-agent AI workforce.
    founder

  3. Memory Gardens

    Jan 2022 - Sep 2023

    Founder & CEO · McKinney, TX

    Built a Web3 + AI startup from concept to market: a decentralized 3D media-legacy app shipped on iOS and Android, concept to public beta in 12 months.

    • Led a 16-person globally distributed team across 5 countries (US, Nigeria, Pakistan, Ukraine, Canada).
    • During a cash crunch, used AI to backfill roles after layoffs, the spark for the human + AI-agent workforce model I run today.
    • Reached ~5,000 installs in early market validation.
    founder

  4. JPMorgan Chase & Co.

    Nov 2020 - Aug 2021

    Vice President, Enterprise Cloud Solution Architecture · Plano, TX

    Set cloud integration and transformation direction across business lines on Google Cloud and AWS; shaped the blockchain department's infrastructure and firm-wide reusable multi-cloud blueprints, IAM guardrails, and SRE frameworks.

  5. DTCC

    Nov 2013 - Jul 2018

    Associate Director & Sr. Infrastructure Architect · Dallas, TX

    Led a $5.2M enterprise mobility and security program that unlocked global work-from-anywhere; set architecture standards and drove cross-functional IT and business delivery.

Capabilities

The full stack of the role, strategy through firmware.

The merge, made concrete. Every item is backed by shipped work, not coursework.

GenAI & Agents

Where I spend most of my time.

  • LLMs & prompt engineering
  • Agentic & multi-agent systems
  • RAG (vector / hybrid / semantic)
  • Model Context Protocol (MCP)
  • Azure AI Foundry / OpenAI
  • Anthropic Claude
  • LangChain · AutoGen · Langflow · LiteLLM
  • Fine-tuning & evals
  • Voice AI (STT / TTS)
  • Vision & edge AI
  • AI for robotics · digital twins
  • AI-generated CAD

Cloud & Platform

20 years of enterprise architecture underneath the AI.

  • Azure (primary) · AWS · GCP
  • Container Apps · Kubernetes · Docker
  • Zero-trust / private AI
  • Private endpoints · VNet · Entra ID
  • Key Vault · managed identity
  • Cosmos DB · PostgreSQL / pgvector · Blob
  • Terraform · Bicep · GitHub Actions
  • Cloudflare · Tailscale

Build & Ship

Still hands-on in the codebase.

  • Python · FastAPI
  • TypeScript · Node.js
  • React · Next.js · SvelteKit
  • Solidity · smart contracts
  • Bash · SQL
  • ESP32 / embedded firmware
  • CI/CD & GitOps
  • Infrastructure as Code

Lead & Advise

The executive half of the merge.

  • AI strategy & transformation
  • AI center of excellence stand-up
  • Hybrid human + AI-agent team design
  • Executive advisory & storytelling
  • Program & portfolio management
  • Vendor evaluation & build-vs-buy
  • GTM · P&L · board advisory
  • Mentorship & next-gen leadership
Recognition & voice

A public track record, on the record.

Press & appearances
TEDxHartford 2023 · ~125,000 views

The Illusion of Memory: Can We Truly Digitize Existence?

Watch on the official TEDx channel

Patent-Pending Inventor

Two U.S. provisional patents filed for AI-designed food-production robotics.

AI Thought Leader

6,300+ LinkedIn followers; frequent high-engagement posts on agents, human agency, and AI-native business.

Community Builder

Organizes and mentors at enterprise and public AI hackathons and build groups across the Dallas-Fort Worth AI community.

Let's build

Have something ambitious that needs to ship?

I'm always open to a conversation about frontier AI, agentic systems, and turning hard problems into running products. Based in McKinney / Dallas-Fort Worth, TX. Work anywhere.

ben@peeri.us
Emailben@peeri.usLinkedInin/benpeeriGitHubcryptomonkey2020